4 papers
Beyond Reactivity: Measuring Proactive Problem Solving in LLM Agents
Gil Pasternak, Dheeraj Rajagopal, Julia White +4
LLM-based agents are increasingly moving towards proactivity: rather than awaiting instruction, they exercise agency to anticipate user needs and solve them autonomously. However,…
K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks
Gil Pasternak
Recursive Feature Machines (RFMs) are a class of kernel machines that utilize the Average Gradient Outer Product (AGOP) as a mechanism for feature learning. They have been shown to…
Measuring Risk of Bias in Biomedical Reports: The RoBBR Benchmark
Jianyou Wang, Weili Cao, Longtian Bao +6
Systems that answer questions by reviewing the scientific literature are becoming increasingly feasible. To draw reliable conclusions, these systems should take into account the qu…
GLiNER2: An Efficient Multi-Task Information Extraction System with Schema-Driven Interface
Urchade Zaratiana, Gil Pasternak, Oliver Boyd +2
Information extraction (IE) is fundamental to numerous NLP applications, yet existing solutions often require specialized models for different tasks or rely on computationally expe…